Head to head

Gemini Embedding 001 vs LFM2.5 8B-A1B

On a blended workload of one million input tokens and three million output tokens, Gemini Embedding 001 is 2.6× cheaper than LFM2.5 8B-A1B.

Gemini Embedding 001LFM2.5 8B-A1B
Provider Google Together AI
Input / MTok $0.15 $0.03
Output / MTok $0.12
Cache read / MTok
Context window 32,768
Blended 1M in + 3M out $0.15 $0.39
Status ga ga

Gemini Embedding 001 detail   LFM2.5 8B-A1B detail